CN108836406A - A kind of single laparoscopic surgical system and method based on speech recognition - Google Patents

Abstract

The invention discloses a voice recognition-based single-person laparoscopic surgery system and method, wherein the system includes: a laparoscopic lens, used to acquire video images; a display module, used to display the video images acquired by the laparoscopic lens; mechanical movement The module is used to drive the laparoscopic lens to move; the voice recognition module is used to convert the voice signal into an operation instruction; the driving module is used to receive the operation instruction and drive the mechanical movement module to make corresponding movements. The system and method of the present invention realize the control of the laparoscopic surgery system by a single person through the combination of the speech recognition system and the mechanical moving module, with fast adjustment speed and precise control, avoiding the target field of view error and operation lag caused by the assistant holding the mirror in the past; at the same time It can also be combined with a distance measuring module to prevent the lens from moving forward and damaging tissues when the adjustment speed is too fast, ensuring safety. As a speech recognition-based single-person laparoscopic operation system and method, the present invention can be widely used in the field of medical devices.

Description

A single-person laparoscopic surgery system and method based on speech recognition

technical field

The invention relates to the field of medical devices, in particular to a speech recognition-based single-person laparoscopic surgery system and method.

Background technique

Laparoscopic technology is becoming more and more mature, with the advantages of small intraoperative incision, small trauma, less bleeding, mild postoperative inflammation, quick recovery, small scar, and short hospital stay, and has become the mainstream surgical method. In traditional laparoscopic gastric cancer surgery, the chief surgeon, first assistant, and speculum operator work together to perform the surgery. However, the "single-port laparoscopy" that has emerged in recent years has attracted great attention and research because it can save medical human resource costs. However, the current laparoscopic system can only reduce one assistant—this mainly depends on the training of the surgeon's surgical skills, and does not require much research and development and improvement of surgical instruments, so it is carried out quickly. At the same time, because the replacement of the mirror arm needs to involve the development and improvement of laparoscopic instruments, it is difficult and has not been studied in depth. Just as the "eyes" of the surgeon, the mirror holder helps the surgeon to accurately position the surgical field of view by finely adjusting the position of the laparoscopic lens, but after all, the surgeon's "eyes" are no longer controlled by himself, but by the assistant. There will be a certain error and lag in the target field of view. Therefore, the mirror-holding technique of the mirror-handler, the understanding of the operation, and the tacit understanding with the operator will all affect the progress, fluency, stability and safety of the operation.

In the prior art, the mechanical structure design of the fixed mirror body of the laparoscope is quite mature, such as patents CN203303162U, CN206138352U, a laparoscope fixing device (application number: 201721394836. The circuit signal of the laparoscopic system in the module requires the movement of the lens; however, the existing laparoscopic surgery system still requires multiple people to operate, and the requirements for the operator are high. Limited, the understanding of the surgical scene is out of sync with the surgeon and the long-term operation of holding the mirror can easily lead to hand tremors, the complexity of the anatomical position in gastric cancer surgery, etc., and the base is prone to skew, the screen is shifted, and the surgeon cannot keep up with the operation Due to the rhythm and other conditions, many gastric cancer operations in clinical practice cannot obtain the best surgical field and angle, which may affect the accuracy of the surgeon's operation and the fluency and quality of the operation, and may even increase the risk of tissue damage during the operation (already Studies have shown that the clarity and stability of the surgical field in laparoscopic surgery can improve the safety of surgery); at the same time, when the quality of the mirror is not good, the quality of the corresponding surgical video will decline, and the advantages of laparoscopic surgery in teaching cannot be maximized. It is unfavorable for young doctors to learn laparoscopic surgery and improve surgical communication and reference among peers.

Contents of the invention

In order to solve the above-mentioned technical problems, the object of the present invention is to provide a single-person laparoscopic surgery system based on speech recognition to realize rapid adjustment and high safety.

In order to solve the above-mentioned technical problems, another object of the present invention is to provide a single-person laparoscopic operation method based on speech recognition to realize rapid adjustment and high safety.

The technical solution adopted in the present invention is: a single-person laparoscopic surgery system based on speech recognition, including

Laparoscopic lens for acquiring video images;

Display module, is used for displaying the video image that laparoscopic lens obtains;

The mechanical moving module is used to drive the laparoscopic lens to move;

A voice recognition module for converting voice signals into operating instructions;

The driving module is used for receiving operation instructions and driving the mechanical moving module to perform corresponding movements.

Further, it also includes a ranging module arranged on the laparoscope lens, which is used to send a stop instruction to the driving module when an obstacle is detected during the movement.

Further, when the ranging module detects that the distance to the object is less than the set threshold during the movement, it determines that an obstacle is detected, and sends a stop instruction to the driving module.

Further, the priority of the stop instruction is higher than that of the operation instruction.

Further, the speech recognition module is used to recognize the speech signal representing the direction and convert it into an operation instruction corresponding to the direction of movement.

Another technical solution adopted in the present invention is: a single-person laparoscopic operation method based on speech recognition, comprising the following steps:

A. The display module displays the video images acquired by the laparoscopic lens;

B. The voice recognition module collects voice signals and converts them into operating instructions;

C. The driving module receives the operation instruction and drives the mechanical moving module to move accordingly, thereby driving the laparoscopic lens to move.

Further, step D is also included: during the process of moving the laparoscopic lens driven by the mechanical moving module, the distance measuring module arranged on the laparoscopic lens sends a stop command to the driving module when an obstacle is detected.

Further, in the step D, when the ranging module detects that the distance to the object is less than the set threshold, it determines that an obstacle is detected, and sends a stop instruction to the driving module.

Further, the priority of the stop instruction is higher than that of the operation instruction.

Further, the step B specifically includes: the speech recognition module recognizes the speech signal representing the direction and converts it into an operation instruction corresponding to the direction of movement.

The beneficial effects of the system and method of the present invention are: through the combination of the voice recognition system and the mechanical moving module, a single person can control the laparoscopic surgery system, the adjustment speed is fast, the control is precise, and the target field of view error caused by the assistant holding the mirror in the past is avoided And operation lag; at the same time, it can also be combined with the distance measurement module to prevent the lens from moving forward and damage the tissue when the adjustment speed is too fast, ensuring safety.

Description of drawings

Fig. 1 is the structural block diagram of the system of the present invention;

Fig. 2 is a flowchart of the steps of the method of the present invention.

Detailed ways

The specific embodiment of the present invention will be further described below in conjunction with accompanying drawing:

Referring to Fig. 1, a single-person laparoscopic surgery system based on speech recognition includes

Laparoscopic lens for acquiring video images;

Display module, is used for displaying the video image that laparoscopic lens obtains;

The mechanical moving module is used to drive the laparoscopic lens to move;

A voice recognition module for converting voice signals into operating instructions;

The driving module is used for receiving operation instructions and driving the mechanical moving module to perform corresponding movements.

The voice recognition module can collect the voice signal of the chief surgeon, and recognize and convert the syllables of the voice signal. For example, the chief surgeon can issue "advance", "retreat", "left", "right", "up" or "down" in real time during the operation voice, the voice recognition module recognizes and converts it, and converts it into a corresponding operation command. For example, if a "back" syllable is recognized, the original scaling parameter λ1 is reduced by one unit, and the corresponding action is to control the mechanical movement module. Drive the laparoscopic lens back a distance of one unit. If a syllable of "advance" is recognized, one unit will be added to the original zoom parameter λ1 accordingly. The corresponding action is to control the mechanical movement module to drive the laparoscopic lens forward by one unit. distance. Similarly, for the recognized "left", "right", "up" and "down" voices, the horizontal axis parameter λ2 and the vertical axis parameter λ3 are adjusted accordingly.

Since the system of the present invention can be operated by a single person and the adjustment speed is relatively fast, in order to prevent the lens from continuing to advance and damage the tissue caused by the surgeon’s voice command too fast, further as a preferred embodiment, it also includes a distance measuring module arranged on the laparoscopic lens , which is used to send a stop command to the drive module when an obstacle is detected during motion.

As a further preferred embodiment, when the ranging module detects that the distance to the object is less than a set threshold during the movement, it judges that an obstacle is detected and sends a stop command to the drive module, and the threshold is usually set to 1cm.

As a further preferred implementation manner, the priority of the stop instruction is higher than that of the operation instruction.

As a further preferred embodiment, the speech recognition module is used to recognize the speech signal representing the direction and convert it into an operation instruction corresponding to the direction of movement.

With reference to Fig. 2, a kind of single-person laparoscopic operation method based on speech recognition comprises the following steps:

A. The display module displays the video images acquired by the laparoscopic lens;

B. The voice recognition module collects voice signals and converts them into operating instructions;

C. The driving module receives the operation instruction and drives the mechanical moving module to move accordingly, thereby driving the laparoscopic lens to move.

As a further preferred embodiment, it also includes step D: when the mechanical moving module drives the laparoscopic lens to move, the ranging module installed on the laparoscopic lens sends a stop command to the driving module when an obstacle is detected.

As a further preferred embodiment, in the step D, when the ranging module detects that the distance to the object is less than the set threshold, it determines that an obstacle is detected, and sends a stop instruction to the driving module.

As a further preferred implementation manner, the priority of the stop instruction is higher than that of the operation instruction.

As a further preferred embodiment, the step B specifically includes: the speech recognition module recognizes a speech signal representing a direction and converts it into an operation instruction corresponding to the direction of motion.

The above is a specific description of the preferred implementation of the present invention, but the invention is not limited to the described embodiments, and those skilled in the art can also make various equivalent transformations or replacements without violating the spirit of the present invention. These equivalent modifications or replacements are all within the scope defined by the claims of the present application.

Claims (10)

1. A single-person laparoscopic surgery system based on voice recognition, characterized in that: a laparoscopic lens is included for obtaining video images; Display module, is used for displaying the video image that laparoscopic lens obtains; The mechanical moving module is used to drive the laparoscopic lens to move; A voice recognition module for converting voice signals into operating instructions; The driving module is used for receiving operation instructions and driving the mechanical moving module to perform corresponding movements. 2. A single-person laparoscopic surgery system based on voice recognition according to claim 1, characterized in that: it also includes a ranging module arranged on the laparoscopic lens, which is used for detecting obstacles during the movement. The drive module issues a stop command. 3. The single person laparoscopic surgery system based on speech recognition according to claim 2, characterized in that: when the ranging module detects that the distance object is less than the set threshold during the movement, it is judged that an obstacle is detected, and Send a stop command to the drive module. 4. A single-person laparoscopic surgery system based on voice recognition according to claim 1 or 2, characterized in that: the priority of the stop command is higher than that of the operation command. 5. A single-person laparoscopic surgery system based on speech recognition according to claim 1, characterized in that: the speech recognition module is used to recognize the speech signal representing the direction and convert it into an operation instruction corresponding to the direction of motion . 6. A single person laparoscopic surgery method based on speech recognition, is characterized in that, comprises the following steps: A. The display module displays the video images acquired by the laparoscopic lens; B. The voice recognition module collects voice signals and converts them into operating instructions; C. The driving module receives the operation instruction and drives the mechanical moving module to move accordingly, thereby driving the laparoscopic lens to move. 7. A single-person laparoscopic surgery method based on voice recognition according to claim 6, further comprising step D: during the process of the mechanical moving module driving the laparoscopic lens to move, using the The ranging module of the lens sends a stop command to the driving module when an obstacle is detected. 8. A single-person laparoscopic surgery method based on speech recognition according to claim 7, characterized in that: in the step D, when the ranging module detects that the distance from the object is less than the set threshold, it is judged that an obstacle is detected , and send a stop command to the drive module. 9 . The single-person laparoscopic operation method based on voice recognition according to claim 6 or 7, characterized in that: the priority of the stop instruction is higher than that of the operation instruction. 10. A single-person laparoscopic surgery method based on speech recognition according to claim 6, wherein the step B is specifically: the speech recognition module recognizes the speech signal representing the direction and converts it into a corresponding Operation instructions for the direction of movement.